{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JE4IUCRA4NXFPVAABUBIZQUPXP","short_pith_number":"pith:JE4IUCRA","schema_version":"1.0","canonical_sha256":"49388a0a20e36e57d4000d028cc28fbbde1a3e2559ed99fff5ea5427355cb4f2","source":{"kind":"arxiv","id":"2411.15620","version":1},"attestation_state":"computed","paper":{"title":"Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hwiyeon Yoo, Hyeokjoon Kwon, Jinwoo Ahn","submitted_at":"2024-11-23T18:13:27Z","abstract_excerpt":"Recent advent of vision-based foundation models has enabled efficient and high-quality object detection at ease. Despite the success of previous studies, object detection models face limitations on capturing small components from holistic objects and taking user intention into account. To address these challenges, we propose a novel foundation model-based detection method called FOCUS: Fine-grained Open-Vocabulary Object ReCognition via User-Guided Segmentation. FOCUS merges the capabilities of vision foundation models to automate open-vocabulary object detection at flexible granularity and al"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.15620","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-23T18:13:27Z","cross_cats_sorted":[],"title_canon_sha256":"aa4626caedb41a48dbd6174b8a9d8f6a7bd63f17805a05280866959168ac40f5","abstract_canon_sha256":"4f9fc1de7dfbbc963969fd883a9e8b3fe5dd2dbf10e2f3bd302f1aa884360b56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:38.234897Z","signature_b64":"hk22by81qQXjYx/yVOQMaaVad/uczfeZnXv7DDYeg4Ps1EWA/hnHCy/oqmz7/7b77FIuz0MfQ0HmO499m74nCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49388a0a20e36e57d4000d028cc28fbbde1a3e2559ed99fff5ea5427355cb4f2","last_reissued_at":"2026-07-05T09:39:38.234418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:38.234418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-Grained Open-Vocabulary Object Recognition via User-Guided Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hwiyeon Yoo, Hyeokjoon Kwon, Jinwoo Ahn","submitted_at":"2024-11-23T18:13:27Z","abstract_excerpt":"Recent advent of vision-based foundation models has enabled efficient and high-quality object detection at ease. Despite the success of previous studies, object detection models face limitations on capturing small components from holistic objects and taking user intention into account. To address these challenges, we propose a novel foundation model-based detection method called FOCUS: Fine-grained Open-Vocabulary Object ReCognition via User-Guided Segmentation. FOCUS merges the capabilities of vision foundation models to automate open-vocabulary object detection at flexible granularity and al"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15620","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2411.15620/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.15620","created_at":"2026-07-05T09:39:38.234482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15620v1","created_at":"2026-07-05T09:39:38.234482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15620","created_at":"2026-07-05T09:39:38.234482+00:00"},{"alias_kind":"pith_short_12","alias_value":"JE4IUCRA4NXF","created_at":"2026-07-05T09:39:38.234482+00:00"},{"alias_kind":"pith_short_16","alias_value":"JE4IUCRA4NXFPVAA","created_at":"2026-07-05T09:39:38.234482+00:00"},{"alias_kind":"pith_short_8","alias_value":"JE4IUCRA","created_at":"2026-07-05T09:39:38.234482+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP","json":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP.json","graph_json":"https://pith.science/api/pith-number/JE4IUCRA4NXFPVAABUBIZQUPXP/graph.json","events_json":"https://pith.science/api/pith-number/JE4IUCRA4NXFPVAABUBIZQUPXP/events.json","paper":"https://pith.science/paper/JE4IUCRA"},"agent_actions":{"view_html":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP","download_json":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP.json","view_paper":"https://pith.science/paper/JE4IUCRA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15620&json=true","fetch_graph":"https://pith.science/api/pith-number/JE4IUCRA4NXFPVAABUBIZQUPXP/graph.json","fetch_events":"https://pith.science/api/pith-number/JE4IUCRA4NXFPVAABUBIZQUPXP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP/action/storage_attestation","attest_author":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP/action/author_attestation","sign_citation":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP/action/citation_signature","submit_replication":"https://pith.science/pith/JE4IUCRA4NXFPVAABUBIZQUPXP/action/replication_record"}},"created_at":"2026-07-05T09:39:38.234482+00:00","updated_at":"2026-07-05T09:39:38.234482+00:00"}